Instructions to use timm/vit_base_patch16_224.augreg_in21k_ft_in1k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_base_patch16_224.augreg_in21k_ft_in1k with timm:
import timm model = timm.create_model("hf-hub:timm/vit_base_patch16_224.augreg_in21k_ft_in1k", pretrained=True) - Transformers
How to use timm/vit_base_patch16_224.augreg_in21k_ft_in1k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="timm/vit_base_patch16_224.augreg_in21k_ft_in1k") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_base_patch16_224.augreg_in21k_ft_in1k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training parameters
#1
by ondratybl - opened
Please, could you share training parameters for this model? I.e. something of the form like
./distributed_train.sh 4 /data/imagenet --model vit_base_patch16_224.augreg_in21k_ft_in1k --sched cosine --epochs 150 --warmup-epochs 5 --lr 0.4 --reprob 0.5 --remode pixel --batch-size 256 --amp -j 4